Method and System for Gait Detection of a Person

2. The method according to claim 1, wherein the probability estimator comprises a Bayes estimator.

4. The method according to claim 3, wherein the one or more biomechanical features comprise at least one of the following features: intensity of acceleration norm, mean of acceleration norm, maximum peak of normalised autocorrelation function of acceleration norm, peak-to-peak value of normalised autocorrelation function of acceleration norm, maximum peak of spectrum of acceleration norm, sharpness of maximum peak of spectrum of acceleration norm, step frequency of gait, posture of the individual at a sensor location, ratio of energy of high to low frequencies of acceleration norm, zero crossing rate of mean-removed acceleration norm, spectral edge frequency of acceleration norm, randomness score of acceleration norm, and kurtosis of acceleration norm.

5. The method according to claim 1, wherein the segmented acceleration signal comprises three substantially orthogonal acceleration components (Az [n], Ay [n], Az [n]).

6. The method according to claim 1, further comprising training the probability estimator by using a training data set prior to determining the estimated probability value.

7. The method according to claim 1, wherein the accelerometer is worn on a wrist of the individual.

8. The method according to claim 1, wherein the determination is made based on the acceleration signal from a single accelerometer only.

10. The method according to claim 9, wherein a is between 0.1 and 0.3, while b is between 5 and 15.

11. The method according to claim 9, wherein if the condition k−m+1≤b is not fulfilled, the determination threshold is set to 0.5+c for gait occurrence, and is set to 0.5−c for non-gait occurrence such that gait is determined to occur if PT[n] >(0.5+c), while non-gait is determined to occur if PT[n]<(0.5−c), and for (0.5−c)≤PT [n]≤(0.5+c), the last non-ambiguous determination is assigned to window n.

12. The method according to claim 11, wherein c is between 0.02 and 0.2.

13. The method according to claim 10, wherein a is between 0.15 and 0.25.

14. The method according to claim 10, wherein b is between 8 and 12.

15. The method according to claim 12, wherein c is between 0.05 and 0.15.